何森

Evaluation code for SSIM

1

Hi, Thanks for the amazing work. Can you please share the code for evaluation (e.g., SSIM)?

Hi, Can you please provide the testing pairs used for MPV dataset? Thanks

Flow Addition

1

Hi, Thanks for the great work. When I was reading the paper and the code, I found the flow refinement is done by a sampling operation rather than addition as...

What is the image input for inference?

1

Thanks for this great work! After going through the code, I got some questions. 1. In the first stage of training discrete VAE, we already trained a [code book](https://github.com/lucidrains/DALLE-pytorch/blob/d7bd745b23424e5a47c0db7e7ab093542427b22d/dalle_pytorch/dalle_pytorch.py#L128). Why...

Hi, Thanks for your great work. When I load the deepfashion dataset, I found the size of image is 256X256 but the size of the heat map is 256X176. How...

nan loss

8

Hi, Thanks for sharing your code. I used your code to train on FFHQ dataset. The resolution is 128X128. All losses become NaN after few training iterations. The training losses...

Dear Pan, I am Sen, a phd student from the university of Exeter. Recently I am doing the literature review of saliency prediction and found your work. Therefore, I want...